Exploratory analysis and implementation of machine learning techniques for predictive assessment of fraud in banking systems

Moreira, Miguel Ângelo Lellis; Rocha, Claudio de Souza; Silva, Diogo Ferreira de Lima; Castro, Marcos Alexandre Pinto de; Costa, Igor Pınheıro de Araújo; Gomes, Carlos Francısco Sımões; Santos, Marcos dos

doi:10.1016/j.procs.2022.11.156

Cited by 21 publications

(16 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Third, we did not perform a comprehensive bibliometric analysis, which could have provided additional insights into the existing literature on mental distress screening tools. While bibliometric analysis is a useful tool to explore the scientific landscape of a specific research field, we faced methodological difficulties in conducting a systematic literature review and machine learning-based analysis for the predictive assessment of screening tools in this study [ 77 , 78 ]. Future researchers should consider conducting bibliometric analysis to identify the current state of the field and to highlight any research gaps that need to be addressed.…”

Section: Discussionmentioning

confidence: 99%

The Brain Overwork Scale: A Population-Based Cross-Sectional Study on the Psychometric Properties of a New 10-Item Scale to Assess Mental Distress in Mongolia

et al. 2023

View full text Add to dashboard Cite

Identifying mental distress is a complex task, particularly when individuals experience physical symptoms. Traditional self-report questionnaires that detect psychiatric symptoms using emotional words may not work for these individuals. Consequently, there is a need for a screening tool that can identify both the physical and mental symptoms of mental distress in individuals without a clinical diagnosis. Our study aimed to develop and validate a scale that measures mental distress by measuring the extent of brain overwork, which can be extrapolated as the burden of mental distress. In this population-based cross-sectional study, we recruited a total of 739 adults aged 16–65 years from 64 sampling centers of a cohort in Mongolia to validate a 10-item self-report questionnaire. Internal consistency was measured using McDonald’s ω coefficient. Test–retest reliability was analyzed using intraclass correlation coefficients. Construct and convergent validities were examined using principal component analysis (PCA) and confirmatory factor analysis (CFA). The Hospital Anxiety and Depression Scale (HADS) and the abbreviated version of World Health Organization Quality of Life (WHOQOL-BREF) were used to evaluate criterion validity. Among the participants, 70.9% were women, 22% held a bachelor’s degree or higher, 38.8% were employed, and 66% were married. The overall McDonald’s ω coefficient was 0.861, demonstrating evidence of excellent internal consistency. The total intraclass correlation coefficient of the test–retest analysis was 0.75, indicating moderate external reliability. PCA and CFA established a three-domain structure that provided an excellent fit to the data (RMSEA = 0.033, TLI = 0.984, CFI = 0.989, χ2 = 58, p = 0.003). This 10-item scale, the Brain Overwork Scale (BOS-10), determines mental distress in three dimensions: excessive thinking, hypersensitivity, and restless behavior. All the items had higher item-total correlations with their corresponding domain than they did with the other domains, and correlations between the domain scores had a range of 0.547–0.615. BOS-10 correlated with HADS, whereas it was inversely correlated with WHOQOL-BREF. In conclusion, the results suggest that BOS-10 is a valid and reliable instrument for assessing mental distress in the general population. The scale screens for mental distress that is characterized by subjective symptoms such as excessive thinking, hypersensitivity, and restless behavior. The current findings also demonstrate that the BOS-10 is quantitative, simple, and applicable for large group testing. This scale may be useful for identifying at-risk individuals who may require further evaluation and treatment for mental distress.

show abstract

Section: Discussionmentioning

confidence: 99%

The Brain Overwork Scale: A Population-Based Cross-Sectional Study on the Psychometric Properties of a New 10-Item Scale to Assess Mental Distress in Mongolia

et al. 2023

View full text Add to dashboard Cite

show abstract

“…According to Choo (2015), those who engage in bribery and corruption would constantly look for new opportunities to commit crimes, launder money obtained via corruption and avoid detection by law enforcement and other government authorities. This sort of corruption includes using cryptocurrencies to finance terrorists, digital currency frauds, online fraud, e-banking system security, Internet banking fraud, transnational financial crime and the use of machine learning in banking (Choo, 2015;Gonz alvez-Gallego and P erez-C arceles, 2021;Kelley et al, 2023;Moreira et al, 2022;Sun et al, 2023;Wodo et al, 2021).…”

Section: Literature Reviewmentioning

confidence: 99%

“…This sort of corruption includes using cryptocurrencies to finance terrorists, digital currency frauds, online fraud, e-banking system security, Internet banking fraud, transnational financial crime and the use of machine learning in banking (Choo, 2015; Gonzálvez-Gallego and Pérez-Cárceles, 2021; Kelley et al. , 2023; Moreira et al. , 2022; Sun et al.…”

Section: Literature Reviewmentioning

confidence: 99%

Political stability and corruption nexus: an international perspective on European and Asian countries

Beju,

Ciupac-Ulici,

Bresfelean

2024

JRF

View full text Add to dashboard Cite

PurposeThis paper aims to investigate the impact of political stability on corruption by drawing upon a sample encompassing both developed and developing European and Asian countries.Design/methodology/approachThe dataset, sourced from the Refinitiv database, spans from July 2014 to May 2022. Panel data techniques, specifically pooled estimation and dynamic panel data [generalized method of moments (GMM)] are employed. The analysis encompasses both fixed and random effects models to capture country-specific cross-sectional effects. To validate our findings, we perform a robustness test by including in the investigation four control variables, namely poverty, type of governance, economic freedom and inflation. To test heterogeneity, the dataset is further divided into two distinct subsamples based on the countries’ locations.FindingsEmpirical findings substantiate that political stability (viewed as the risk of government destabilization) has a positive and significant impact on corruption in all analyzed samples of European and Asian countries, though some differences are observed in various subsamples. When we take into account the control variables, these analysis results are robust.Research limitations/implicationsThis research provided a panel data analysis with GMM, while other empirical methodologies could also be used, like the difference-in-difference approach. However, our results should be validated by extending the time and the sample to a worldwide sample and using alternative measures of corruption and political stability. Moreover, our focus was on a linear and unidirectional relationship between the considered variables, but it would be interesting to test in our further research a non-linear and bidirectional correlation between them. Furthermore, we have introduced in the robustness test only four economic variables, but to consolidate our findings, we plan to include socioeconomic and demographic variables in future studies.Practical implicationsThese outcomes imply that authorities should be aware of the necessity of implementing anti-corruption policies designed to establish effective agencies and enforcement structures for combating systemic corruption, to improve the political environment and the quality of institutions and to apply coherent economic strategies to accelerate economic growth because higher political stability and sustainable development determine a decrease in levels of corruption.Social implicationsAt the microeconomic level, the survival of organizations may be in danger from new types of corruption and money laundering. Therefore, in order to prevent financial harm, the top businesses worldwide should respond to instances of corruption through strengthened supervisory procedures. This calls for the creation of a mechanism inside the code of conduct where correct reporting of suspected situations of corruption would have a prompt procedure to be notified of. To avoid corruption in operational procedures, national plans and policies should be developed by government officials, executives and legislators on a national level, as well as by senior management and the board of directors on an organizational level. This might lower organizations' extra corruption-related expenses, assure economic growth and improve global welfare.Originality/valueA novel feature of our research resides in its broad examination of a sizable sample of European and Asian countries regarding the nexus between corruption and political stability. The paper also investigates a less explored topic in economic literature, namely the impact of political stability on corruption. Furthermore, the study depicts policy recommendations, outlining effective and reasonable measures aimed at improving the political landscape and combating corruption.

show abstract

“…In other words, ML allows computers to learn from data and make decisions or predictions without explicit programming, namely, it is the creation and implementation of algorithms capable of facilitating decisions and forecasts. [8][9]17] The progress in the ML area has created powerful opportunities for the automation of the EDA processes. [18] Indeed, in the ML industry, EDA has been widely used, for example: to detect fraud in the banking system [17], in the study of chronic kidney diseases in medicine [8] or for analog-mass spectrometry of the ocean world [9].…”

mentioning

confidence: 99%

“…[8][9]17] The progress in the ML area has created powerful opportunities for the automation of the EDA processes. [18] Indeed, in the ML industry, EDA has been widely used, for example: to detect fraud in the banking system [17], in the study of chronic kidney diseases in medicine [8] or for analog-mass spectrometry of the ocean world [9].…”

mentioning

confidence: 99%

Exploratory Data Analysis Possibility in the Meaning Space Using Large Language Models

Lyashkevych,

Shuvar

2024

ELIT

View full text Add to dashboard Cite

Today, data analysis plays a key role in studying and using large amounts of information to make informed decisions. Thus data is one of the most valuable resources and analytical tools are becoming increasingly important. Data analysis allows us to identify patterns and relationships between different factors. As for the methods of analysis, they are very diverse and depend on the specific task and the nature of the data, each method has its advantages and limitations, and the choice of a particular one depends on the context.Recent investigations have proved that LLM showed good results in textual information analysis and might be one of the textual analytical tools. Therefore, the main focus of our research is centred around the ability of LLM to perform data interpretation operations, arithmetic and statistical operations in the meaning space. In the evaluation of the proposed concepts, simple cases were considered. It was enough to better understand the effectiveness of LLM as one of the tools for exploratory data analysis.The practical results of the research indicate that the concept has some advantages over the closest analogues, as well as identify several scientific problems that can be solved in subsequent studies. Additionally, research tools were developed as a chatbot system in the Telegram environment.

show abstract

Exploratory analysis and implementation of machine learning techniques for predictive assessment of fraud in banking systems

Cited by 21 publications

References 31 publications

The Brain Overwork Scale: A Population-Based Cross-Sectional Study on the Psychometric Properties of a New 10-Item Scale to Assess Mental Distress in Mongolia

The Brain Overwork Scale: A Population-Based Cross-Sectional Study on the Psychometric Properties of a New 10-Item Scale to Assess Mental Distress in Mongolia

Political stability and corruption nexus: an international perspective on European and Asian countries

Exploratory Data Analysis Possibility in the Meaning Space Using Large Language Models

Contact Info

Product

Resources

About